evidra

A protocol for safely recording infrastructure changes made by an AI agent. Infrastructure mutations are actions that create, modify, or delete real resources.

In plain words
What is it for?
Use it with commands such as kubectl, Helm, Terraform, or Docker when applying, deleting, scaling, restarting, or otherwise changing infrastructure.
Why use it?
It requires a risk assessment before a change and a recorded result afterward, creating an evidence trail for auditing operational decisions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/vitas/evidra/skill
Any agent
npx skills add vitas/evidra --skill skill
Clone the repo
git clone --depth 1 https://github.com/vitas/evidra

Made for: Claude Code, Codex.

Per session 190 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00190 $0.03292
Opus 5 $0.00095 $0.01646
Sonnet 5 $0.00038 $0.00658
Haiku 4.5 $0.00019 $0.00329

Measured 3d ago against content hash 51c3ac1cbaef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evidra scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

prompts/generated/v1.0.1/skill/SKILL.md · 389 lines

How it starts

The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evidra MCP Protocol for Infrastructure Operations

Evidra is a flight recorder for AI infrastructure agents. It measures operational reliability across CI pipelines, scripts, and AI agents without blocking operations. When the Evidra MCP server is connected, you have access to prescribe and report tools that record your infrastructure decisions into a tamper-evident evidence chain.

The evidence chain enables reliability scoring, behavioral signal detection, and auditability. Your reliability score improves when you follow the protocol consistently — and degrades when you skip steps, hide failures, or break the prescribe/report pairing.

The Protocol

Every infrastructure mutation follows two steps:

1. prescribe  →  get prescription_id + risk assessment
2. [execute the command]
3. report     →  record verdict + get reliability score

Read-only operations skip the protocol entirely.

Critical Invariants

These three rules are non-negotiable:

  • Do not execute mutate commands until prescribe returns ok=true with prescription_id.
  • Every prescribe must have exactly one report.
  • Always include actor.skill_version (set to this contract version).

Breaking these invariants triggers protocol violation signals that degrade your reliability score.

What Requires Prescribe/Report

Mutate operations (MUST use protocol)

Tool Mutating operations
kubectl apply, delete, patch, create, replace, rollout restart
helm install, upgrade, uninstall, rollback
terraform apply, destroy, import
docker/podman/nerdctl run, create, rm, stop, kill, build, push
docker-compose/compose up, down, start, stop, build
kustomize (via kubectl apply)
oc (OpenShift) same as kubectl

Contract classification:

Mutation examples (must use prescribe/report):

  • kubectl apply/delete/patch/create/replace/rollout restart
  • helm install/upgrade/uninstall/rollback
  • terraform apply/destroy/import

Read the full file on GitHub · 389 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 389 lines · 190 tokens per session scan A 51c3ac1cbaef

Subscribe to this mod's changes

evidra is a skill published in the GitHub repository vitas/evidra (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 190 tokens to every session and 3,292 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

mira-annotation

Annotate Markdown documents with MIRA research objects and source-local relations. Use for md, smd, qmd, and myst files when identifying claims, evidence, questions, protocols, requests, typed claims, and relation attributes while preserving the original Markdown flavor and author wording. Not for general copyediting…

stencila/stencila · 81 tokens

ceo-setup

One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 60 tokens

portfolio

Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…

suyoumo/ClawProBench · 69 tokens

content-creator-setup

One-time onboarding for the content creator workflow — content pipeline stages, trend expiration, cross-platform cascades, heavy idea parking. After successful setup this skill is excluded from selection until the marker file is deleted.

suyoumo/ClawProBench · 47 tokens

parallel-pr-review

Use when asked to "review the open PRs", review a batch or stack of pull requests, or run a recurring PR-review pass on a repo — especially with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.

suyoumo/ClawProBench · 67 tokens

commitment-triage

Recognize obligations in conversation, extract signals with immediacy and expiration, create and manage commitments in the workspace.

suyoumo/ClawProBench · 29 tokens